• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.63-66
• /
• 2015

3차원 영상을 생성하기 위해 스테레오 매칭을 통해 깊이 정보를 획득한다. 이때 발생하는 경계영역과 텍스처가 부족한 부분의 깊이정보 부정확성 문제를 해결하기 위해 영상 분할 기반 스테레오 매칭 방법을 제안한다. 일반적으로 사용하는 윈도우 기반 스테레오 매칭 결과를 기반으로 분할된 영상 내에서 최적의 변위 값을 재 할당함으로서 깊이정보의 정확성을 향상시킬 수 있다. Mean-shift는 참조 영상에서 화소 간 평균값 차이가 최대가 되는 영역들을 반복적으로 찾는다. 유사한 평균값을 갖는 영역들을 기반으로 영상을 분할하는 것을 Mean-shift를 이용한 영상분할 이라고 한다. 분할된 영상은 각 영역을 대표하는 패치 구조를 가지고 있어 참조 영상에 포함되어있는 잡음에 강인한 특성을 지닌다. 스테레오 매칭을 통해 화소별로 변위 값을 할당해주는 대신, 분할된 영상을 이용하여 각 분할 영역에 동일한 변위 값을 할당한다. 분할된 영상에 동일한 변위 정보를 할당할 경우 객체와 배경의 경계영역에서 잘못된 변위 값이 할당되는 경우가 발생한다. 이러한 경계 영역의 변위정보 부정확성을 보완하기 위해 화소의 기울기 항을 비용 값 계산 과정에 추가하여 단점을 보완한다. 최종 비용 값 계산을 통해 획득한 초기 변위 지도에 중간 값 필터를 적용하여 분류된 영역에 동일한 변위 값을 할당한다. 제안한 방법을 적용하여 경계영역의 정확도가 향상된 최종 변위 지도를 획득한다.

• Korean Journal of Food Science and Technology
• /
• v.33 no.4
• /
• pp.427-436
• /
• 2001

The effects of storage form (paddy and milled rice) and storage period (1, 2, and 3 years) of rice at low temperature $(4^{\circ}C)$ on physicochemical properties of milled and cooked rice and sensory characteristics of cooked rice were investigated. The proximate compositions except moisture content of rice decreased as the storage period increased. Water binding capacity, solubility and swelling power of rice flour decreased with the extended storage period. In the amylogram, the initial pasting temperature, paste viscosity and breakdown of paddy rice flour slurry decreased after 2 years of storage. Moisture content of cooked rice increased while the amount of water evaporated during cooking decreased. These trends were obvious with the longer storage period. Lightness and yellowness of cooked rice were greatly changed after 3 years of storage, regardless of storage form. Texture profile analysis of cooked rice by Texture Analyzer revealed that hardness, fracturability, gumminess were gradually increased while adhesiveness decreased as the storage period of rice increased. A trained panel found that color intensity, intactness of grains, rancid flavor, rice bran flavor, wet cardboard flavor, hardness and chewiness of cooked rice increased with the longer storage period. However, glossiness, transparency, plumpness, puffed corn flavor, dairy flavor, boiled egg white flavor, sweet taste, adhesiveness to lips, smoothness and inner moisture decreased with the extended storage period up to 3 years. Instrumental hardness was highly correlated with sensory hardness.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.572-587
• /
• 2008

The Self-organizing Feature Map(SOFM) that is one of unsupervised neural networks is a very powerful tool for data clustering and visualization in high-dimensional data sets. Although the SOFM has been applied in many engineering problems, it needs to cluster similar weights into one class on the trained SOFM as a post-processing, which is manually performed in many cases. The traditional clustering algorithms, such as t-means, on the trained SOFM however do not yield satisfactory results, especially when clusters have arbitrary shapes. This paper proposes automatic clustering on trained SOFM, which can deal with arbitrary cluster shapes and be globally optimized by graph cuts. When using the graph cuts, the graph must have two additional vertices, called terminals, and weights between the terminals and vertices of the graph are generally set based on data manually obtained by users. The Proposed method automatically sets the weights based on mode-seeking on a distance matrix. Experimental results demonstrated the effectiveness of the proposed method in texture segmentation. In the experimental results, the proposed method improved precision rates compared with previous traditional clustering algorithm, as the method can deal with arbitrary cluster shapes based on the graph-theoretic clustering.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.1
• /
• pp.112-119
• /
• 2002

We propose an enhanced wavelet packet image coder algorithm which is based on the coefficients partition. The proposed wavelet packet image coder uses the first-order entropy to reduce the total compression time, and achieves low bit rates and rate-distortion performance by the zero-tree based coding using correlations between coefficients partition. This new algorithm represents new parent-children relationships for reducing image reconstruction error using the correlations between each frequency subbands and then the wavelet packet coefficients are Partitioned by a new order. The computer simulations demonstrate higher PSNR under the same bit rate and improved image compression time and enhanced rate control compare with conventional algorithms. From the simulation results, it is shown that the encoding and decoding process of proposed coder are much simple and accurate than present method against texture images , which include many mid-frequency elements.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.886-888
• /
• 2005

본 논문에서는 복부 CT 영상에서 폐 부위를 빠르게 분할하기 위하여 그래픽 하드웨어를 사용한 레벨 셋 기법을 제안한다. 제안방법은 다음과 같이 세 단계로 구성된다. 첫째, 레벨 셋 기법을 그래픽 하드웨어로 효율적으로 구현하기 위하여 초기 레벨 셋 값 설정과 설정된 레벨 셋 값을 텍스처메모리에 저장한다. 둘째, 레벨 셋 기법의 가장 중요한 부분인 속도함수를 그래픽 하드웨어의 빠른 연산을 이용하여 계산하고, 레벨 셋 값을 갱신한다. 셋째, 갱신된 레벨 셋 값을 통하여 제로-레벨 셋을 찾는다. 본 논문에서는 제안 방법을 평가하기 위하여 일련의 복부 CT 영상을 사용하며, 육안평가 및 수행시간 면에서 기존 소프트웨어 기반 레벨 셋 기법과 비교분석한다. 실험결과 본 제안방법은 소프트웨어 기반 레벨 셋 기법과 분할결과를 동일하게 유지하면서 평균 9배 빠르게 폐 부위를 분할하였다.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.974-976
• /
• 1995

Segmentation of image data is an important problem in computer vision, remote sensing, and image analysis. Most objects in the real world have textured surfaces. Segmentation based on texture information is possible even if there are no apparent intensity edges between the different regions. There are many existing methods for texture segmentation and classification, based on different types of statistics that can be obtained from the gray-level images. In this paper, we use a neural network model --- ART-2 (Adaptive Resonance Theory) for textures in an image, proposed by Carpenter and Grossberg. In our experiments, we use Walsh matrix as feature value for textured image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.546-549
• /
• 2020

본 논문에서는 최신 비디오 코딩 기술에서 잔차(Residual)신호 변환을 효율적으로 수행하기 위한 부동기저(Basis)를 사용하는 방법을 제안한다. 기존의 DCT-II 나 DST-VII 과 같은 고정 기저를 사용하는 방법은 대부분의 잔차신호들에 대해 효과적으로 비상관화(decorrelation)를 수행하지만 복잡한 잔차 신호일수록 성능이 떨어지는 문제가 있었다. 이러한 압축 성능하락 문제를 줄이기 위하여 PCA(Principle Component Analysis) 방법 중 하나인 KLT(Karhunen-Loeve Transform)를 이용하여 부동(floating) 변환 기저를 유도하는 방법을 제안한다. 기존의 KLT 를 이용한 변환 커널 유도 방법들의 문제점인 부호화기 및 복호화기 계산 복잡도를 줄이기 위하여 KL 커널을 분해가능한(Separable) 2 개의 1 차원 커널로 유도하는 방법을 제안하고, 원본 잔차신호와 유사한 텍스처를 찾아 커널을 예측하는 과정을 간소화하는 방법을 제안한다. 제안하는 방법은 HEVC 에서 실험되었으며 정지영상 코딩 Main-Profile 에서 평균 1.4%가량의 BD-PSNR(Bjontegaard Delta-Peak Signal to Noise Ratio) 성능 향상을 보였으며 특히 스크린 컨텐츠 영상에서 최대 4.5%의 성능 향상을 보인다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.5
• /
• pp.85-91
• /
• 2015

This paper presents a novel frame rate up-conversion (FRUC) algorithm. Existing algorithms, in general, employ rectangular blocks for motion estimation and arbitrary shape of an actual object region cannot be precisely represented. On the other hand, the proposed wedge-shaped block partitioning algorithm partitions a rectangular block into two wedge-shaped blocks using the texture information, which makes better approximation for an actual object region. The wedge-shaped block partitioning algorithm as well as the adaptive motion vector prediction algorithm is used to reliably estimate the actual motion. Experimental results show that the proposed FRUC algorithm is superior to existing algorithms up to 1.988dB in PSNR and 0.0167 in SSIM comparisons.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.99-112
• /
• 2019

Cracks on pavement surfaces are critical signs and symptoms of the degradation of pavement structures. Image-based pavement crack detection is a challenging problem due to the intensity inhomogeneity, topology complexity, low contrast, and noisy texture background. In this paper, we address the problem of pavement crack detection and segmentation at pixel-level based on a Deep Neural Network (DNN) using gray-scale images. We propose a novel DNN architecture which contains a modified U-net network and a high-level features network. An important contribution of this work is the combination of these networks afforded through the fusion layer. To the best of our knowledge, this is the first paper introducing this combination for pavement crack segmentation and detection problem. The system performance of crack detection and segmentation is enhanced dramatically by using our novel architecture. We thoroughly implement and evaluate our proposed system on two open data sets: the Crack Forest Dataset (CFD) and the AigleRN dataset. Experimental results demonstrate that our system outperforms eight state-of-the-art methods on the same data sets.

• Journal of Korea Multimedia Society
• /
• v.17 no.1
• /
• pp.69-76
• /
• 2014

It is hard to represent massive terrain data in real-time even using recent graphics hardware. In order to process massive terrain data, mesh simplification method such as continuous Level-of-Detail is commonly used. However, existing GPU-based methods using quad-tree structure such as geometry splitting, produce lots of vertices to traverse the quad-tree and retransmit those vertices back to the GPU in each tree traversal. Also they have disadvantage of increase of tree size since they construct the tree structure using texture. To solve the problem, we proposed GPU-base chunked LOD technique for real-time terrain rendering. We restrict depth of tree search and generate chunks with tessellator in GPU. By using our method, we can efficiently render the terrain by generating the chunks on GPU and reduce the computing time for tree traversal.